# talk-normal-llm-prompt

This skill steers an LLM away from filler and padded phrasing while keeping the useful content. Use it for API calls, project rules, or direct assistant instructions.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 479 installs · ★ 88
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/talk-normal-llm-prompt/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/talk-normal-llm-prompt

## What it does

talk-normal-llm-prompt supplies a system prompt for shorter, plainer model responses. It targets empty affirmations, corporate wording, and decorative bullet points without asking the model to drop useful information. The main file is `prompt.md`; the repository also includes rule history, contribution guidance, comparison results, and optional shell helpers.

You can paste the prompt into an interface’s system instructions, prepend it to `.cursorrules`, or pass it through an API `system` parameter. The examples cover OpenAI, Anthropic Claude, Google Gemini, and Ollama, plus an `asknormal` shell wrapper. API usage needs the relevant environment key such as `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, or `GEMINI_API_KEY`; the shell examples use `jq`. In Claude Code, the skill is installed with `npx skills add` and stored at `~/.claude/skills/talk-normal-llm-prompt/SKILL.md`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill talk-normal-llm-prompt -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/talk-normal-llm-prompt/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/talk-normal-llm-prompt/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill talk-normal-llm-prompt -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/talk-normal-llm-prompt/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill talk-normal-llm-prompt -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/talk-normal-llm-prompt/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/trending-skills talk-normal-llm-prompt
```

2. **Manually: put the files in place**
- File: `.github/skills/talk-normal-llm-prompt/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill talk-normal-llm-prompt -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/trending-skills --path skills/talk-normal-llm-prompt
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/talk-normal-llm-prompt/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill talk-normal-llm-prompt -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/talk-normal-llm-prompt/SKILL.md

## When to use it
- trim verbose model responses
- remove hollow openings and confirmations
- apply one response style across project AI rules
- pass a system prompt into an API request
- compare output with and without the prompt

## Example prompts
- Use `talk-normal-llm-prompt` and answer this question in one short paragraph.
- Rewrite the response without filler, empty agreement, or padded bullet points.
- Add `talk-normal-llm-prompt` before the existing system instructions for this API call.

## Similar
- [skill-creator](https://affpapa.org/en/nevibecode/skills/skill-creator.md) — skill · 414180 installs
- [writing-for-agents](https://affpapa.org/en/nevibecode/skills/writing-for-agents.md) — skill · 466719 installs
- [media-use](https://affpapa.org/en/nevibecode/skills/media-use.md) — skill · 1100000 installs
- [mcp-builder](https://affpapa.org/en/nevibecode/skills/mcp-builder.md) — skill · 130949 installs
- [subagent-driven-development](https://affpapa.org/en/nevibecode/skills/subagent-driven-development.md) — skill · 237746 installs
- [orchestration](https://affpapa.org/en/nevibecode/skills/orchestration.md) — skill · 350300 installs

From the same set: [reason-machines/trending-skills](https://affpapa.org/en/nevibecode/by/reason-machines/trending-skills.md) — 186 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md